AI engineering glossary · Agents tools MCP
What is workflow versus agent?
Workflow versus agent: A design distinction: a workflow follows paths that developers define in code, with model calls at fixed points, while an agent lets the model decide its own steps and tool use. Workflows are cheaper, faster and more predictable; agents suit open-ended problems where the steps cannot be listed in advance.
Workflow versus agent: an example
Sending every support email through classify, then draft, then send is a workflow. A bot that decides whether to look up an order, issue a refund or escalate is an agent.
Related terms
More Agents tools MCP terms
- Action
- Action space
- Agent autonomy level
- Agent benchmark
- Agent card
- Agent evaluation
- Agent handoff
- Agent loop
Where you learn it
Workflow versus agent is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.